INDEX
Explanations
mentions of bowling and related activities
New Auto-Interp
Negative Logits
нак
-0.17
uzz
-0.15
celik
-0.15
="""
-0.15
serter
-0.14
akin
-0.14
Sinn
-0.14
tti
-0.14
fact
-0.13
Directions
-0.13
POSITIVE LOGITS
Guards
0.16
Gol
0.16
592
0.15
ach
0.14
588
0.14
cus
0.14
CTION
0.14
æ»
0.14
489
0.14
æĿ¿
0.14
Activations Density 0.012%